Graphic Processing Units (GPUs) are commonly used to accelerate Convolutional Neural Networks (CNNs) for object detection and classification. As CNNs are employed in safety-critical applications, such as autonomous vehicles, their reliability must be carefully evaluated. In this work, we combine the accuracy of microarchitectural simulation with the speed of software fault injection to investigate the reliability of CNNs executed in GPUs. First, with a detailed microarchitectural fault injection on a GPU model (FlexGripPlus), we characterize the effects of faults in critical and user-hidden modules (such as the Warp Scheduler and the Pipeline Registers) in the computation of convolution over a suitably selected subset of tiles. Then, with software fault injection, we propagate the fault effects in the CNN. Thanks to our approach we are able, for the first time, to analyze the impact of faults affecting GPUs' hidden modules on a whole CNN execution (LeNET) without undermining the reliability evaluation correctness.

Combining architectural simulation and software fault injection for a fast and accurate CNNs reliability evaluation on GPUs / Rodriguez Condia, Josie E.; Fernandes dos Santos, Fernando.; Sonza Reorda, Matteo; Rech, P.. - ELETTRONICO. - 2021-:(2021), pp. 1-7. (Intervento presentato al convegno 39th IEEE VLSI Test Symposium, VTS 2021 tenutosi a usa nel 2021) [10.1109/VTS50974.2021.9441044].

Combining architectural simulation and software fault injection for a fast and accurate CNNs reliability evaluation on GPUs

Rodriguez Condia, Josie E.;Sonza Reorda, Matteo;Rech, P.
2021

Abstract

Graphic Processing Units (GPUs) are commonly used to accelerate Convolutional Neural Networks (CNNs) for object detection and classification. As CNNs are employed in safety-critical applications, such as autonomous vehicles, their reliability must be carefully evaluated. In this work, we combine the accuracy of microarchitectural simulation with the speed of software fault injection to investigate the reliability of CNNs executed in GPUs. First, with a detailed microarchitectural fault injection on a GPU model (FlexGripPlus), we characterize the effects of faults in critical and user-hidden modules (such as the Warp Scheduler and the Pipeline Registers) in the computation of convolution over a suitably selected subset of tiles. Then, with software fault injection, we propagate the fault effects in the CNN. Thanks to our approach we are able, for the first time, to analyze the impact of faults affecting GPUs' hidden modules on a whole CNN execution (LeNET) without undermining the reliability evaluation correctness.
2021
978-1-6654-1949-9
File in questo prodotto:
File Dimensione Formato  
Combining_Architectural_Simulation_and_Software_Fault_Injection_for_a_Fast_and_Accurate_CNNs_Reliability_Evaluation_on_GPUs.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 261.02 kB
Formato Adobe PDF
261.02 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2913700